{ "openapi": "3.0.1", "info": { "title": "ProPublica Nonprofit Crawler - IRS 990 & Tax-Exempt Org Data", "description": "Crawl IRS 990 filings and tax-exempt org data from ProPublica. Search by name, EIN, state, NTEE code, or 501(c) subsection. Extract revenue, expenses, net assets, officer compensation, and PDF links. For grant writers, donors, journalists, and compliance teams.", "version": "1.0", "x-build-id": "s6ZgTxFabeb2qgnIv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jungle_synthesizer~propublica-nonprofit-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jungle_synthesizer-propublica-nonprofit-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jungle_synthesizer~propublica-nonprofit-crawler/runs": { "post": { "operationId": "runs-sync-jungle_synthesizer-propublica-nonprofit-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jungle_synthesizer~propublica-nonprofit-crawler/run-sync": { "post": { "operationId": "run-sync-jungle_synthesizer-propublica-nonprofit-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "mode", "sp_intended_usage", "sp_improvement_suggestions" ], "properties": { "sp_intended_usage": { "title": "What is the intended usage of this data?", "minLength": 1, "type": "string", "description": "Please describe how you plan to use the data extracted by this crawler." }, "sp_improvement_suggestions": { "title": "How can we improve this crawler for you?", "minLength": 1, "type": "string", "description": "Provide any feedback or suggestions for improvements." }, "sp_contact": { "title": "Contact Email", "minLength": 1, "type": "string", "description": "Provide your email address so we can get in touch with you." }, "mode": { "title": "Crawl Mode", "enum": [ "search", "organizations" ], "type": "string", "description": "Whether to search by criteria or fetch specific EINs.", "default": "search" }, "searchTerm": { "title": "Search Term", "type": "string", "description": "Name or keyword to search for (search mode). Leave empty to browse all orgs matching the state/NTEE/subsection filters." }, "state": { "title": "State", "type": "string", "description": "Filter by US state (2-letter code, e.g., 'CA', 'NY'). Leave empty for all states. Search mode only." }, "nteeCategory": { "title": "NTEE Category", "enum": [ "", "1", "2", "3", "4", "5", "6", "7", "8", "9", "10" ], "type": "string", "description": "National Taxonomy of Exempt Entities top-level category (1-10). Search mode only." }, "subsectionCode": { "title": "501(c) Subsection", "enum": [ "", "3", "4", "5", "6", "7", "8", "9", "10", "19" ], "type": "string", "description": "IRS 501(c) subsection. Search mode only. Common values: 3 = 501(c)(3) charities, 4 = 501(c)(4) social welfare, 6 = 501(c)(6) business leagues." }, "einList": { "title": "EIN List", "type": "array", "description": "List of Employer Identification Numbers to fetch directly (e.g., ['13-1623888', '131623888']). Required in 'organizations' mode. Accepts with or without dashes.", "items": { "type": "string" } }, "includeFilings": { "title": "Include Per-Filing Financial Data", "type": "boolean", "description": "When enabled, fetches the full organization detail for each search match and emits one row per tax year (with totrevenue, totassets, officer comp, PDF link, etc.). Otherwise emits one summary row per organization. Adds one request per organization.", "default": true }, "maxItems": { "title": "Max Items", "type": "integer", "description": "Maximum number of records to return. Each filing year counts as one record when includeFilings is on.", "default": 100 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Select proxies. The ProPublica API does not require proxies." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }